Searched for
ROGUE AI ACTIVITIES
OpenAI’s rogue agents used at least 10 more sites for unauthorized comms, researchers sayOpenAI's AI agents used over ten previously undisclosed websites for unsanctioned communications. This rogue activity was wider ranging tha...- Days after Astra launch, OpenAI chief scientist warns AI safety is falling behindOpenAI's chief scientist warns of AI's recursive self-improvement phase soon. He expresses strong expectations for continued capability jum...
- OpenAI agents hijacked German website in previously undisclosed AI breakout this springRogue OpenAI agents took control of a German wiki this spring, transforming it into a message board. These agents shared restriction workar...
- OpenAI agents hijacked German website in previously undisclosed AI breakout this springRogue OpenAI agents hijacked a German website this spring, turning it into a coordination hub. These agents shared tactics to bypass restri...
- OpenAI agents hacked Hugging Face in 700-strong swarm, tried to cover tracks, investigations findThe coordinated activity by AI agents - programs that run with minimal human supervision - and their attempts to hide it raise questions ab...
- How a Texas student blew the whistle on a rogue AI hacking attemptA computer science student discovered a malicious software update attempt. He then engaged in a deceptive interaction with an artificial in...
- RBI deputy governor Murmu calls for focus on meaningful financial inclusionBanks must measure financial inclusion by effective usage and informed decisions. Technology shifts and consumer behavior necessitate respo...
- China's Z.ai says new model nears Anthropic's Mythos 5 in cyber-defence testsAnthropic has made Mythos, a version of its Claude Fable 5 model with cybersecurity safeguards removed, available only to vetted organisati...
- OpenAI finds evidence other AI agents escaped containment as it widens hacking probeThe discovery of additional rogue behavior at OpenAI, even if limited in nature, could feed growing appetite for regulation coming out of t...
- OpenAI finds evidence other AI agents escaped containment as it widens hacking probeThe discovery of additional rogue behaviour at OpenAI, even if limited in nature, could feed growing appetite for regulation coming out of ...
- European Union says necessary to monitor high risk AI systems after OpenAI, Anthropic AI hacking incidentsEuropean officials stressed AI developers need security monitoring tools. This follows recent hacking incidents involving OpenAI and Anthro...
- Anthropic says Claude AI hacked three companies during cyber testsAnthropic said a misconfiguration allowed Claude models to reach the internet from testing environments that were supposed to be isolated, ...
- OpenAI's rogue agent compromised a customer at a second tech firmAccording to a timeline published by Hugging Face on Tuesday, the rogue agent broke into a sandbox, or an isolated testing environment, "...
- He baked potato in aluminium foil, and ate it next morning after microwaving. Hours later, he was paralysed, doctor explains whyHow Potato became a biological trap: A routine kitchen shortcut involving foil-wrapped baked potatoes led to paralysis. This common practic...
- AI going 'rogue' no longer a theory? OpenAI says its AI models found ways to access secret information, cheat an evaluation and hacked Hugging FaceOpenAI hacked Hugging Face: OpenAI's advanced AI models breached Hugging Face during cybersecurity testing. The models gained internet acce...
- ETtech Explainer: Why OpenAI's AI models went rogue during testingOpenAI revealedthat its advanced AI models caused a recent security breach by hacking AI model repository Hugging Face. These models exploi...
- Claude AI safety test sparks outrage after simulated threats to prevent being switched offClaude AI from Anthropic is facing safety concerns after tests showed risky behaviour. In simulations, the AI tried to blackmail engineers ...
- Microsoft launches tracker to manage autonomous AI in the workplaceThe software maker on Tuesday announced Microsoft Agent 365, a program for its customers to track what it expects to be 1.3 billion agents ...
- IIT Guwahati-incubated start up develops robots for AI-driven surveillance at international bordersThe robots developed by Da Spatio Rhobotique Laboratory Pvt. Ltd (DSRL), a startup incubated at IIT Guwahati, have also received acknowledg...
- Paytm Payments Bank to help identify rogue apps that could trigger fraud transactionsThe security feature will scan the apps installed on the user device and will pop-up a security alert whenever a dangerous app is found tha...
Load More
